Launches on August 23, 2026

Email inbox API for AI agents. Give every agent its own real email address, receive mail as structured webhooks, and reply in-thread over REST. A complete multi-tenant mail server in Rust: inbound and outbound, DKIM/SPF/DMARC/ARC, MTA-STS, DANE, three-tier anti-spam.

Coverage, security and code quality for coding agents

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, makes no LLM calls.

g8s (The Gatekeepers): Zero-trust multi-agent orchestrator. Brain/supervisor delegates to muscle/worker via briefs, receipts, heartbeats, and lifecycle cleanup.

AI Harness - JIT policy routing, MCP/Skill capability acquisition, shared machine runtime registry

Inference control plane using pi-ai and rust-based bun (1.4+).

要望を Issue にして、受け入れ条件が全て埋まり・検証が緑・レビュー指摘0件になるまで実装しきる Claude Code プラグイン

Daily LLM benchmark on Poople (poople.io): one-shot word ladders to POOP, scored against provable optimal, accuracy vs cost via OpenRouter

A visual inspection agent that remembers: it compares every capture against the stored baseline of the same asset, decides in code what to do next, and stops for a human when a finding is severe. OpenCV 5 (ALIKED + LightGlue), five MCP tools, one arm64 Lambda.

Personal finance tracker — TanStack Start + Hono RPC, Supabase auth, Drizzle, AI statement import

WIP

Agent-facing MCP server for Google Search Console, GA4, and Workspace with scoped OAuth

Terminal coding agent — the human harness for the nacelle SDK

A framework for generic RAG in enterprise environment

Observe-and-advise coaching reactor: watches spectral-sight's live game-state feed and prints fair-play, real-time coaching cues. Advises, never acts.

Purchasing, supplier and procurement management for the Cores ecosystem

Agentic AI payment fraud detection platform combining XGBoost, GraphSAGE, learned score fusion, PostgreSQL, FastAPI, HITL workflows, and evidence-grounded LLM investigations.